Anti-congestion urban traffic control method and system

Abstract

The invention discloses an anti-congestion urban traffic control method and system, and belongs to the technical field of traffic control, and the method comprises the steps: S1, collecting traffic information, and obtaining traffic data; s2, constructing a dynamic disturbance model, and predicting the future traffic condition by capturing the dynamic change of the traffic data; s3, acquiring the real-time change of the queuing length in the traffic flow according to the traffic condition; s4, analyzing the change conditions of the traffic flow and the vehicle driving speed, predicting the state of the signal lamp based on the historical data and the traffic conditions, and calculating the timing of the signal lamp according to the change of the queuing length; s5, analyzing and acquiring a congested road section, a congested time period and a congested duration in a week, and acquiring a shunting node adjacent to the congested road section to prompt to shunt in advance; s6, providing the traffic information to a driver in real time; according to the anti-congestion urban traffic management and control method and system provided by the invention, the road use efficiency can be improved, the traffic safety can be ensured, and the occurrence of congestion conditions can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic control, and particularly to an anti-congestion urban traffic control method and system. Background Technique

[0002] Traffic control refers to the management and control of the passage of vehicles and pedestrians on roads and other traffic-related activities in accordance with legal regulations. This management usually includes diverting, restricting, or prohibiting passage within a specific time to ensure the safety, order, and smoothness of road traffic.

[0003] With the rapid advancement of urbanization, the urban population has increased sharply, and the number of motor vehicles in possession has also been continuously rising. This rapid development trend has led to the urban traffic demand far exceeding the carrying capacity of traffic infrastructure, and the traffic congestion problem has become increasingly severe.

[0004] Traffic congestion not only significantly increases the travel time of residents, reducing travel efficiency, but also causes serious economic losses. It is estimated that the economic losses caused by traffic congestion, such as fuel waste and increased time costs, reach billions or even tens of billions of yuan every year. In addition, when congested, vehicles idle or travel at low speeds for a long time, which will cause a sharp increase in exhaust emissions, have a great negative impact on the urban air quality, and endanger the health of residents.

[0005] Currently, urban traffic control mainly relies on traditional signal control and on-site traffic police command. When traditional signals are regulated, they are usually regulated by time periods and cycles, and it is inconvenient to flexibly regulate according to real-time traffic flow and congestion conditions. Although on-site traffic police command can relieve congestion to a certain extent, the manpower is limited, it is difficult to cover every corner of the city, and the work of traffic police is also greatly restricted under bad weather conditions. Therefore, it is extremely urgent to develop a more intelligent and efficient anti-congestion urban traffic control method and system to meet the needs of urban traffic development, improve traffic operation efficiency, and improve the urban traffic environment. Summary of the Invention

[0006] The purpose of the present invention is to provide an anti-congestion urban traffic control method and system to solve the problems existing in the above background technique.

[0007] To achieve the above purpose, the present invention provides an anti-congestion urban traffic control method, including the following steps:

[0008] S1. Collect traffic information to obtain traffic data;

[0009] S2. Construct a dynamic disturbance model, and predict the future traffic conditions by capturing the dynamic changes of traffic data;

[0010] S3. Obtain the real-time change of the queue length in the traffic flow according to the future traffic conditions;

[0011] S4. By analyzing the changes in traffic flow and vehicle driving speed, based on historical data and traffic conditions, predict the signal light status, input the prediction results into the optimization algorithm, and calculate the signal light timing according to the change of the queue length;

[0012] S5. Analyze and obtain the congested sections, congested time periods and congestion durations within a week according to historical traffic data and queue length, and obtain the diversion nodes adjacent to the congested sections to prompt early diversion;

[0013] S6. Provide the above traffic information to the driver in real time.

[0014] Preferably, in step S1, the specific steps of obtaining traffic data are as follows:

[0015] S11. Real-time collect traffic conditions through the deployed Beidou intelligent integrated pole;

[0016] S12. Transmit the collected traffic conditions to the traffic application platform through the network;

[0017] S13. In the traffic application platform, preprocess the collected traffic conditions to obtain traffic data and display it on the Beidou intelligent integrated pole in real time.

[0018] Preferably, the Beidou intelligent integrated pole in step S11 includes a vertical pole, a traffic light and a monitoring device vertically arranged with the vertical pole. A photovoltaic panel and a lighting device are arranged at the top of the vertical pole. An environmental monitoring sensor and a lane indicator for one-way traffic are arranged below the photovoltaic panel. An information release display board and an edge intelligent computing box are arranged in the middle of the vertical pole; through the set Beidou intelligent integrated pole, traffic flow, environmental meteorology, traffic status and other information are collected in real time, improving the comprehensive perception ability of the road.

[0019] Preferably, the specific steps of step S2 include:

[0020] S21. Preprocess the traffic data obtained in step S1;

[0021] S22. Extract the features related to traffic status from the preprocessed data, including time features, space features, traffic flow features and environmental features;

[0022] S23. Screen out the features that have a significant impact on traffic conditions;

[0023] S24. Build a dynamic perturbation model, identify the factors that cause perturbations to traffic conditions, and quantify these factors as perturbation terms in the model so that it can reflect the impact of these factors on traffic conditions in real time;

[0024] S25. Divide the preprocessed data into a training set, a validation set, and a test set. Use the training set data to train the constructed model, optimize the model parameters by minimizing the loss function, and monitor the model performance using the validation set.

[0025] S26. Evaluate the trained model using the test set data. Input the real-time collected traffic data into the model, and predict the traffic conditions (including traffic flow, vehicle speed, congestion level, etc.) in the future for a certain period of time (such as the next 15 minutes, 30 minutes, 1 hour) according to the output of the model.

[0026] Preferably, the traffic conditions in step S2 include traffic flow, vehicle speed, and congestion level. The queue length in step S3 is used as an indicator to measure the congestion level, and its calculation formula is:

[0027]

[0028] where q is the traffic flow, in vehicles per hour; T is the duration of the vehicle queuing phenomenon, in hours; v is the vehicle speed, in kilometers per hour; 3600 / q is the time interval between the front ends of adjacent vehicles passing through the same section, in seconds per vehicle.

[0029] Preferably, based on the queue length in step S3, the travel time of active motor vehicles in the area is introduced as another evaluation indicator for traffic congestion, and its calculation formula is:

[0030]

[0031] where N is the total number of active vehicles in the area within a certain period of time; t i is the time taken for active vehicles to pass through a certain area within a certain period of time.

[0032] Preferably, the specific steps of step S4 include:

[0033] S41. Model the historical traffic flow and speed data, and analyze their periodic, trend, and random characteristics.

[0034] S42. Based on the historical traffic flow, speed data, and the historical signal light status data, establish a signal light status prediction model, and output the signal light status at different future times.

[0035] S43. According to the queue length calculated in step S3, and based on the changes in the queue lengths of each lane currently, obtain the signal light timing plan, and determine the durations of red lights, green lights, and yellow lights.

[0036] Preferably, the specific steps of obtaining the congestion period in step S5 include:

[0037] S51. Obtain the traffic intersection nodes.

[0038] S52. Identify the vehicle speeds of all lanes based on traffic intersection nodes;

[0039] S53. Generate congestion nodes when the lowest vehicle speed is lower than a preset value, and determine the congested sections based on the congestion nodes.

[0040] The present invention also provides an anti-congestion urban traffic control system, including an information collection module, a prediction module, a congestion assessment module, a signal light control module, a congested section analysis module, a diversion module, and an information release module;

[0041] The information collection module is used to collect traffic information to obtain traffic data;

[0042] The prediction module is used to predict future traffic conditions by constructing a dynamic perturbation model;

[0043] The congestion assessment module evaluates the congestion situation by introducing the queue length and the travel time in the active motor vehicle area as evaluation indicators of the congestion degree;

[0044] The signal light control module is used to calculate the signal light timing plan according to the change of the congestion situation and determine the duration of each state of the signal light;

[0045] The congested section analysis module is used to analyze the traffic data and the congestion situation to identify the congested sections;

[0046] The diversion module is used to obtain the diversion nodes adjacent to the congested sections to prompt diversion;

[0047] The information release module is used to provide the traffic data collected and analyzed to the drivers in real time.

[0048] Therefore, by adopting the above anti-congestion urban traffic control method and system, the present invention has the following beneficial effects:

[0049] (1) By integrating multiple devices using the Beidou intelligent integrated pole, it can collect multi-dimensional information such as traffic flow, environmental meteorology, and traffic status in real time, improve the comprehensive road perception ability, and provide a comprehensive and accurate data basis for subsequent traffic analysis and decision-making;

[0050] (2) By constructing a dynamic perturbation model, through capturing and analyzing the dynamic changes of traffic data, it can effectively predict future traffic conditions, know the traffic situation in advance, and gain time for traffic management and regulation;

[0051] (3) By analyzing data such as traffic flow, vehicle speed, and queue length to predict the signal light status and calculate the timing, it can dynamically adjust the signal light duration according to the real-time traffic situation, improve the road traffic efficiency, reduce the vehicle waiting time, and relieve traffic congestion;

[0052] (4) Not only uses the queue length as the congestion measurement index, but also introduces the travel time in the active motor vehicle area to evaluate traffic congestion from multiple dimensions, more accurately identify the congestion situation. At the same time, by analyzing historical data, determine the congested sections, time periods and durations, and obtain diversion node prompts to divert in advance, which helps to balance the traffic flow and avoid the deterioration of congestion;

[0053] (5) Provide all kinds of traffic information collected and analyzed to drivers in real time, help drivers plan routes in advance, avoid congested sections, improve travel efficiency and enhance travel experience.

[0054] The technical solution of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0055] Figure 1 It is a flowchart of a congestion prevention urban traffic control method of the present invention;

[0056] Figure 2 It is a flowchart of obtaining traffic data in an embodiment of the present invention;

[0057] Figure 3 It is a flowchart of predicting future traffic conditions in an embodiment of the present invention;

[0058] Figure 4 It is a flowchart of signal timing calculation in an embodiment of the present invention;

[0059] Figure 5 It is a flowchart of obtaining congested sections in an embodiment of the present invention. Detailed Embodiments

[0060] The following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0061] A congestion prevention urban traffic control system includes an information collection module, a prediction module, a congestion evaluation module, a signal control module, a congested section analysis module, a diversion module and an information release module;

[0062] The information collection module is used to collect traffic information to obtain traffic data;

[0063] The prediction module is used to predict future traffic conditions by constructing a dynamic perturbation model;

[0064] The congestion evaluation module evaluates the congestion situation by introducing the queue length and the travel time in the active motor vehicle area as evaluation indicators of the congestion degree;

[0065] A signal light control module, which is used to calculate a signal light timing plan according to the change of congestion situation and determine the duration of each state of the signal light;

[0066] A congested section analysis module, which is used to analyze traffic data and congestion situation to identify congested sections;

[0067] A diversion module, which is used to obtain diversion nodes adjacent to the congested section to prompt diversion;

[0068] An information release module, which is used to provide the traffic data collected and analyzed to drivers in real time.

[0069] As Figure 1 - Figure 2 shown, a congestion prevention urban traffic control method applied to the above control system includes the following steps:

[0070] S1. Collect traffic information to obtain traffic data. The specific steps are as follows:

[0071] S11. Real-time collect traffic conditions through technical means such as deployed Beidou intelligent integrated poles or various sensors and monitoring devices;

[0072] S12. Transmit the collected traffic conditions to the traffic application platform through the network. Through the Beidou intelligent traffic application platform, real-time collect, transmit and analyze and process urban traffic vehicle position data, vehicle basic attribute data, vehicle driving data, road comprehensive state data, traffic space information data, etc., to provide comprehensive services such as high-precision positioning, high-precision navigation, emergency communication guarantee, hazard source identification and disposal, and comprehensive command and decision-making for urban comprehensive traffic, and realize the intelligent management of urban traffic;

[0073] S13. In the traffic application platform, preprocess the collected traffic conditions to obtain traffic data and display it on the Beidou intelligent integrated pole in real time.

[0074] The Beidou intelligent integrated pole includes a vertical pole, a traffic light perpendicular to the vertical pole, and a monitoring device. A photovoltaic panel and a lighting device are arranged at the top of the vertical pole. An environmental monitoring sensor and a lane indication sign for divided driving are arranged below the photovoltaic panel. An information release display board and an edge intelligent computing box are arranged in the middle of the vertical pole; through the set Beidou intelligent integrated pole, real-time collect information such as traffic flow, environmental meteorology and traffic state, and improve the comprehensive perception ability of the road.

[0075] S2. Build a dynamic disturbance model, and predict the future traffic conditions by capturing the dynamic changes of traffic data. As Figure 3 shown, the specific steps include:

[0076] S21. Preprocess the traffic data obtained in step S1;

[0077] S22. Extract features related to traffic conditions from the preprocessed data, including time features, spatial features, traffic flow features, and environmental features;

[0078] S23. Screen out the features that have a significant impact on traffic conditions;

[0079] S24. Construct a dynamic perturbation model, identify the factors that cause perturbations to traffic conditions, and quantify these factors as perturbation terms in the model so that it can reflect the impact of these factors on traffic conditions in real time;

[0080] S25. Divide the preprocessed data into a training set, a validation set, and a test set. Use the training set data to train the constructed model, optimize the model parameters by minimizing the loss function, and monitor the model performance using the validation set;

[0081] S26. Evaluate the trained model using the test set data. Input the real-time collected traffic data into the model and predict the traffic conditions (such as traffic flow, vehicle speed, congestion level, etc.) in the next period of time (such as the next 15 minutes, 30 minutes, 1 hour) according to the output of the model.

[0082] S3. Obtain the real-time change of the queue length in the traffic flow according to the future traffic conditions. In the oversaturated state, the queue length is a key indicator to measure the congestion level. By monitoring and updating the queue length in real time, it can more truly reflect the road network situation in the oversaturated traffic state, not only enhancing the accuracy of the traffic model, but also providing more powerful data support for traffic control decisions. The calculation formula is:

[0083]

[0084] Among them, q is the traffic flow, in vehicles per hour; T is the duration of the vehicle queuing phenomenon, in hours; v is the vehicle speed, in kilometers per hour; 3600 / q is the time interval between the fronts of adjacent vehicles passing through the same section, in seconds per vehicle.

[0085] On the basis of the queue length, introduce the travel time of active motor vehicles through the area as another evaluation index of traffic congestion. The calculation formula is:

[0086]

[0087] Among them, N is the total number of active vehicles in the area within a certain period of time; t i is the time spent by active vehicles passing through a certain area within a certain period of time.

[0088] S4. By analyzing the changes in traffic flow and vehicle driving speed, based on historical data and traffic conditions, predict the signal light status, and input the prediction results into the optimization algorithm. According to the change in the queue length, calculate the signal light timing, as Figure 4 shown. The specific steps include:

[0089] S41. Model the historical traffic flow and speed data, and analyze their periodic, trend, and random characteristics;

[0090] S42. Based on the historical traffic flow, speed data, and the historical status data of signal lights, establish a signal light status prediction model, and output the status of signal lights at different future times;

[0091] S43. According to the queue length calculated in step S3, obtain the signal light timing plan based on the change in the queue length of each lane currently, and determine the durations of red lights, green lights, and yellow lights. During the operation of the signal lights, continuously monitor the traffic conditions and make adjustments according to the real-time data. If the traffic conditions change, the system will re-evaluate and adjust the second allocation of the signal lights to adapt to the new traffic demands. This process can maximize traffic efficiency, reduce congestion and waiting time.

[0092] S5. According to the historical traffic data and queue length, analyze and obtain the congested sections, congested time periods, and congestion durations within a week, and obtain the diversion nodes adjacent to the congested sections to prompt early diversion, as Figure 5 shown. The specific steps include:

[0093] S51. Obtain the traffic intersection nodes;

[0094] S52. Identify the vehicle speeds of all lanes based on the traffic intersection nodes;

[0095] S53. Generate congested nodes when the lowest vehicle speed is lower than the preset value, and determine the congested sections according to the congested nodes.

[0096] S6. Provide the above traffic information to drivers in real time.

[0097] The intelligent transportation control system plays an important role in the intelligent regulation of special vehicles. Special vehicles such as ambulances, fire trucks, police cars, and engineering emergency repair vehicles need to pass quickly in case of emergencies and may require special road priority. To achieve this goal, the intelligent transportation system uses traffic signal control and road monitoring systems to identify special vehicles, ensuring that they obtain priority access rights so as to reach their destinations as soon as possible. In addition, the system can dynamically adjust the road rights of special vehicles, plan the best travel routes for them according to their real-time positions and road conditions, and avoid congested sections. By providing special vehicles with real-time road condition information, such as traffic congestion and road closures, the intelligent transportation system helps special vehicles make wise travel decisions. These intelligent regulation measures greatly improve the travel efficiency of special vehicles and ensure the smooth progress of rescue and emergency tasks in case of emergencies.

[0098] Therefore, by adopting the above urban traffic control method and system for anti-congestion, the present invention can accurately monitor road conditions in real time, quickly identify congestion and accidents. Through intelligent regulation of traffic signals and inducing vehicles to be reasonably diverted, it can greatly improve the road traffic efficiency and reduce the congestion duration. It can also enhance traffic safety, reduce the accident risk, and create a smoother and safer travel experience for citizens.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for preventing urban traffic congestion, characterized in that: The following steps are involved: S1. Collect traffic information to obtain traffic data; S2. Build a dynamic disturbance model to predict future traffic conditions by capturing the dynamic changes of traffic data; S3. Obtain the real-time changes in queue length in traffic flow according to future traffic conditions; S4. By analyzing the changes in traffic flow and vehicle speed, based on historical data and traffic conditions, the status of the traffic lights is predicted, and the prediction results are input into the optimization algorithm to calculate the timing of the traffic lights according to the changes in the queue length; S5. Analyze and obtain the congested sections, congested time periods and congested duration within a week based on historical traffic data and queue lengths, and obtain diversion nodes adjacent to the congested sections to prompt early diversion; S6. Provide the above traffic information to the driver in real time.

2. The method for controlling urban traffic congestion according to claim 1, characterized in that: In step S1, the specific steps of obtaining traffic data are as follows: S11, collect traffic conditions in real time through the deployed Beidou smart integrated poles; S12, transmitting the collected traffic conditions to the traffic application platform via the network; S13. In the traffic application platform, the collected traffic conditions are pre-processed to obtain traffic data, which are then displayed in real time on the Beidou smart integrated pole.

3. The method for controlling urban traffic congestion according to claim 2, characterized in that: The Beidou smart integrated pole in step S11 includes a pole and a traffic light and monitoring equipment arranged vertically to the pole. A photovoltaic panel and lighting equipment are arranged on the top of the pole, and an environmental monitoring sensor and directional lane sign are arranged below the photovoltaic panel. An information release display board and an edge intelligent computing box are arranged in the middle of the pole. Through the Beidou smart integrated pole, traffic flow, environmental weather and traffic status information are collected in real time to improve the comprehensive perception ability of the road.

4. The method for controlling urban traffic congestion according to claim 1, characterized in that: The specific steps of step S2 include: S21, preprocessing the traffic data obtained in step S1; S22, extracting features related to traffic status from the preprocessed data, including time features, spatial features, traffic flow features, and environmental features; S23. Screen out the features that have a significant impact on traffic conditions; S24. Construct a dynamic disturbance model to identify the factors that cause disturbances to traffic conditions and quantify these factors as disturbance terms in the model so that it can reflect the impact of these factors on traffic conditions in real time; S25, dividing the preprocessed data into a training set, a validation set and a test set, using the training set data to train the constructed model, optimizing the model parameters by minimizing the loss function, and using the validation set to monitor the model performance; S26. Use the test set data to evaluate the trained model, input the real-time collected traffic data into the model, and predict the traffic status in the future based on the output of the model.

5. The method for controlling urban traffic congestion according to claim 4, characterized in that: The traffic status in step S2 includes vehicle flow, vehicle speed and congestion degree. The queue length in step S3 is used as an indicator to measure the congestion degree, and its calculation formula is: Among them, q is the traffic flow, in units of vehicles / hour; T is the duration of the vehicle queue, in units of hours; v is the vehicle speed, in units of kilometers / hour; 3600 / q is the time interval between the front ends of two adjacent vehicles passing through the same section, in units of seconds / vehicle.

6. The method for controlling urban traffic congestion according to claim 1, characterized in that: In step S3, based on the queue length, the travel time of active motor vehicle areas is introduced as another evaluation index of traffic congestion, and its calculation formula is: Where N is the total number of active vehicles in the area within a certain period of time; t i It is the time that active vehicles spend passing through a certain area within a certain period of time.

7. The method for controlling urban traffic congestion according to claim 1, characterized in that: The specific steps of step S4 include: S41. Model historical traffic flow and speed data and analyze their periodicity, trend and random characteristics; S42, based on historical traffic flow, speed data and historical status data of traffic lights, establish a traffic light status prediction model to output the status of traffic lights at different times in the future; S43. According to the queue length calculated in step S3 and the change of the current queue length of each lane, a signal light timing plan is obtained to determine the duration of the red light, green light and yellow light.

8. The method for controlling urban traffic congestion according to claim 1, characterized in that: The specific steps of obtaining the congestion period in step S5 include: S51, obtaining a traffic intersection node; S52, identifying the vehicle speeds of all lanes based on the traffic intersection nodes; S53: When the minimum vehicle speed is lower than a preset value, a congestion node is generated, and a congested road section is determined according to the congestion node.

9. An anti-congestion urban traffic control system, characterized by: It includes information collection module, prediction module, congestion assessment module, signal light control module, congestion section analysis module, diversion module and information release module; An information collection module is used to collect traffic information and obtain traffic data; The prediction module is used to predict future traffic conditions by building a dynamic disturbance model; The congestion assessment module evaluates the congestion situation by introducing queue length and travel time in active motor vehicle areas as evaluation indicators of congestion degree; The traffic light control module is used to calculate the traffic light timing plan according to the changes in congestion conditions and determine the duration of each state of the traffic light; Congested road section analysis module, used to analyze traffic data and congestion conditions to identify congested road sections; A diversion module is used to obtain diversion nodes adjacent to congested road sections to prompt diversion; The information release module is used to provide the collected and analyzed traffic data to the driver in real time.

Images